FEATURE Machine Vision
Does quality really require fully- autonomous visual inspection?
Zohar Kantor, VP of sales at self-guided visual inspection software company
Lean.AI, discusses quality managers’ requirements around fully-autonomous machine vision
F
or the public to fully accept driverless vehicles, they must be 100x safer than ordinary cars, states a recent report from the
UK Government’s Centre for Data Ethics and Innovation (CDEI). The policy paper ‘Responsible Innovation in Self-Driving Vehicles’ reveals that we judge driverless cars by much higher standards than we would apply to a human driver. According to the report: “Average improvements in road safety, even if they can be clearly demonstrated, will not engender public trust if crashes are seen as the fault of faceless technology companies or lax regulation, rather than fallible human drivers.” In the field of quality inspection,
there is not the same level of fear, but there are some interesting similarities in people’s willingness to trust autonomous technologies. Ultimately, most quality managers would prefer to retain a degree of control, rather than fully automate the entire process.
The boundaries of automation Despite autonomous quality inspection solutions promising highest levels of automation, surely it is better to have a
20 March 2023 | Automation
human expert intolved? After all, they know the product best, and can provide suitable feedback for the AI model to learn from.
Quality managers and engineers often want to know how the black box makes its decision. Much like the sceptics in the driving example, technology replacing human intuition with artificial intelligence must pass a higher barrier of reliability before it is fully accepted. However, even if this lack of trust could be gradually suprassed, it is questionable whether quality managers really want or need a fully-autonomous system. It is more likely that they would prefer we automate some 80% of the process for example, taking the pain and hassle out of building the model by using artificial intelligence, but allowing them to retain control of the remaining 20% through guided learning.
Self-guided learning At
Lean.AI we recognise there is no escaping the necessity of huge amounts of images, particularly for complex applications. The question is, how do we make the process of building the model a better experience for the user?
Right now, it typically takes two months of creating data sets and tagging data, and that’s just for one camera and one product. It is in this area that AI can make a real difference, making the processes much faster and more bearable for the user.
Quality managers don’t want fully- autonomous visual inspection. That may be partly due to a natural distrust of non- human decision-makers, but it is also a reflection of a genuine need to retain a degree of human input in the process. If we can significantly reduce the time it takes to build the model that runs a self-guided machine-vision system, investing in AI becomes an obvious choice for quality managers. However, although AI may be in the driving seat, it is the user who steers the system, by providing feedback. By retaining that control, we’ll get the best of both worlds: automating the process, whilst allowing the user to provide guidance where needed.
CONTACT:
Lean.AI www.lean-ai-tech.com
automationmagazine.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62
